pytorch/examples

Is total variation loss necessary in fast_neural_style?

Open

#278 建立於 2018年1月3日

在 GitHub 查看
 (0 留言) (1 反應) (0 負責人)Python (21,634 star) (9,429 fork)batch import
good first issuequestion

描述

I notice that there is no total variation loss regularization implemented in the example of fast_neural_style. But the paper declared it and their torch version use it. I'm wondering if total variation loss is necessary or not in style transfer.

貢獻者指南

技術棧
pythonpytorch
領域
machine learningai
議題類型
research
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
3
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
1-3 hours
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
stale
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
clear
前置要求
basic knowledge of neural style transferPyTorch basics
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
30
研究方向
Investigate the fast neural style example in pytorch/examples. Compare the implementation with the original torch version referenced in the paper. Check if total variation loss is absent and whether it affects results. Answer the question by examining the code and possibly running experiments.
Is total variation loss necessary in fast_neural_style? · pytorch/examples#278 | Good First Issue